© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 13058
    Prev
    Next
    INDEX
    Explanations

    verbs related to decreasing or minimizing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to minimizing or decreasing negative impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Found
    -0.88
     Founder
    -0.72
     Americas
    -0.70
    Truth
    -0.69
     Mortal
    -0.68
     Phant
    -0.64
    Lord
    -0.63
    Brit
    -0.62
    Gener
    -0.62
     Mushroom
    -0.61
    POSITIVE LOGITS
    uce
    0.85
    xual
    0.85
    uces
    0.84
    ħĭ
    0.81
     inhib
    0.81
     carbohyd
    0.80
    ahime
    0.77
     emissions
    0.77
     dioxide
    0.77
    icides
    0.76
    Activations Density 0.031%

    No Known Activations